Add SIMD optimization for int_to_float conversion #580
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add SIMD fast paths for converting custom bit-depth floats to f32: - 32-bit float passthrough: Simple bitcast using SIMD - 16-bit float (f16/half-precision): SIMD conversion with scalar fallback for subnormal values The 16-bit float SIMD path handles normal, zero, and inf/nan cases directly, falling back to scalar for the rare subnormal case which requires variable-iteration normalization. Also adds BitDepth::f16() test helper and comprehensive unit tests for the conversion functions.
Benchmark @ fca2520 |
veluca93
reviewed
Dec 22, 2025
|
|
||
| // SIMD 16-bit float (half-precision) to 32-bit float conversion | ||
| // This handles IEEE 754 binary16 format: 1 sign bit, 5 exponent bits, 10 mantissa bits | ||
| simd_function!( |
Member
There was a problem hiding this comment.
I think I would prefer to have a pair of functions I32Vec::store_u16() and F32Vec::load_f16_bits() instead. Those functions function can use _mm256_cvtph_ps on AVX2 (by also requiring the F16C target feature, which is common) and vcvt_f32_f16 on NEON (although the Rust definition erroneously requires the f16 target feature, so we'd have to use inline assembly for now -- fixed in rust-lang/stdarch#1978), and fall back to scalar on SSE4.2.
We then could add store_f16() -- implemented in a similar way -- and use that to speed up the f16 conversion code..
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
SIMD fast paths for the
int_to_floatfunction which converts custom bit-depth floats stored as i32 back to f32.32-bit float: straightforward bitcast via SIMD.
16-bit float (f16): SIMD handles normal values, zeros, and inf/nan. Subnormals fall back to scalar since they need a variable-iteration normalization loop.
Waiting for perf CI to see the impact.